feat: Docker build with idleTimeout patch via postbuild script#50
Open
fazo96 wants to merge 1 commit into
Open
feat: Docker build with idleTimeout patch via postbuild script#50fazo96 wants to merge 1 commit into
fazo96 wants to merge 1 commit into
Conversation
- Add Dockerfile, .dockerignore, and docker-compose.yml - Move idleTimeout sed patch from Dockerfile to scripts/postbuild.mjs - Wire postbuild script into package.json lifecycle - Remove scripts/ from .dockerignore so it's available at build time
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
this commit adds two things:
Some details about idleTimeout patch:
The issue is that if the provider is slow and the whole request takes more than 10 seconds, then it fails with
[Bun.serve]: request timed out after 10 seconds. Pass idleTimeout to configure.on the stdout and "Error in input stream" in the UI.The cause is that by default, bun's serve only has a 10 second timeout for the request. Because LLM streaming can be slow especially with long responses, tool calls or self hosting inference, it makes it unusable in some cases. Unfortunately Nitro v3 does not expose this setting (see nitrojs/nitro#3454), it is only supported in v2 through an environment variable that does not work anymore in v3.
To solve this, I added a quick search and replace in post-build to monkey patch the parameter into the compiled js.